fix(llm-callsite): seed latency-optimized callsites on fresh install#26477
Merged
Conversation
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 2066ebf40e
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
Contributor
Author
|
Addressed in #26506 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Address Codex + Devin feedback on #26286.
PR #26286 changed
LLMSchema.callSitesdefault fromLATENCY_OPTIMIZED_CALLSITE_DEFAULTSto{}to restore schema invariants, but that opened a new regression for fresh installs: migration 040 (which seeds latency-optimized callsites) short-circuits whenconfig.jsondoesn't exist yet, so new users permanently fell through tollm.default(Opus + max effort) for background callsites likenotificationDecision,interactionClassifier,guardianQuestionCopy, etc. — the exact cost/latency regression migration 040 was created to prevent.This extends migration 040 to handle the fresh-install case: when config.json is missing, write a minimal starter config containing just
llm.callSitesseeds.loadConfig()runs after migrations and backfills the remaining schema defaults viadeepMergeMissing, which preserves the seeded callSites while filling inllm.default,profiles, etc. on disk.Provider-aware: reads
llm.default.providerfrom existing config when present (existing-workspace path unchanged); falls back toanthropicfor fresh installs (matches the schema default). This preserves the cross-provider-correctness posture from Codex's separate #26275 concern — the right model is picked per provider via the existingPROVIDER_LATENCY_MODELStable rather than hardcoded Anthropic IDs baked into the schema.No changes to the schema —
LLMSchema.callSitesstays.default({}), preserving the invariant work from #26286.